Journal
LANDSCAPE AND ECOLOGICAL ENGINEERING
Volume 7, Issue 2, Pages 263-274Publisher
SPRINGER JAPAN KK
DOI: 10.1007/s11355-010-0132-1
Keywords
Canopy cover; Thematic map; Satellite image; Classification; Segmentation
Categories
Funding
- Konkuk University
Ask authors/readers for more resources
Canopy cover is one of the most important elements in concealing military structures and enemy reconnaissance. In this study, we propose an algorithm for automatic generation of density measure of percent canopy cover, which is an attribute of the digital Military Map product, using high-resolution satellite images of inaccessible areas. The thematic mapping process of canopy cover can be divided into image classification, segmentation, and texture analysis. QuickBird and SPOT-5 high-resolution images are classified using Landsat images and military maps. Then, forested areas are extracted from the classified images, and closing and opening operations are executed through morphology filtering. The extracted region is divided into unit-zone objects using a segmentation technique, and the percentage of canopy cover of each object is categorized as one of four levels (0-25, 26-50, 51-75, 76-100%). Two methods were used to establish the percentage of canopy cover for each segment: the discriminant method, using statistical analysis, and the classified canopy ratio method, which calculates the percentage of forest in the segment. The discriminant method showed 48% (QuickBird) and 61% (SPOT-5) accuracy and classified canopy ratio method showed 71% (QuickBird) and 87% (SPOT-5) accuracy.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available